METR says it can barely measure Claude Mythos, Palo Alto Networks warns of autonomous AI attackers
METR can barely measure Claude Mythos Preview with its current test suite. Only five out of 228 tasks cover the relevant capability range. Meanwhile, Palo Alto Networks reports that frontier models autonomously chain vulnerabilities, shrinking the time from initial access to…
NYT: 'Meta's Embrace of AI Is Making Its Employees Miserable'
"Meta's embrace of AI is making its employees miserable," reports the New York Times. And "After Meta said late last month that it would start tracking employees' computer use, hundreds of workers spoke up." (One employee even told Meta's CTO in an internal post, "Your…
Researchers may have found a way to stop AI models from intentionally playing dumb during safety evaluations
A study by researchers from the MATS program, Redwood Research, the University of Oxford, and Anthropic examines a safety problem that grows more pressing as AI systems become more capable: "sandbagging," where a model deliberately hides its true abilities and delivers work that…